Whale — blazingly fast, terminal-first AI coding agent for DeepSeek. ~98% prompt cache hit rate, 1M context, MCP tools, dynamic workflows.
-
Updated
Jun 28, 2026 - Go
Whale — blazingly fast, terminal-first AI coding agent for DeepSeek. ~98% prompt cache hit rate, 1M context, MCP tools, dynamic workflows.
deepseek-v4-pro-flash deepseek ai large language model llm mixture of experts moe 1m context window hybrid attention architecture compressed sparse attention csa heavily compressed attention hca manifold constrained hyper deepseek-v4-pro deepseek-v4-flash open source hugging face github repository api access local llm inference vllm ollama
🤖 AI-powered CLI chatbot with multi-provider support, tool-calling capabilities, streaming output, and vision input. Built in C++20.
DeepSeek API 命令行工具 (DeepSeek CLI)。把 DeepSeek 开发者平台封装成 resource/action 子命令的最薄外壳:chat/FIM/models/balance、GJSON 变换、多格式输出、SSE 流式,兼容 DashScope/硅基流动/Moonshot/OpenRouter 等 OpenAI 兼容服务。对标 Anthropic ant CLI。
Run DeepSeek V4 Pro Flash models locally on Windows, macOS, and Linux for fast AI chat and coding assistance.
Automate Windows 11 tasks with an offline, multi-agent AI workstation that runs locally on your own hardware.
Add a description, image, and links to the deepseek-cli topic page so that developers can more easily learn about it.
To associate your repository with the deepseek-cli topic, visit your repo's landing page and select "manage topics."